Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Async
    -0.07
    stricted
    -0.07
    adders
    -0.07
    nostic
    -0.06
    .FileOutputStream
    -0.06
    formed
    -0.06
     dut
    -0.06
     जन
    -0.06
    閉
    -0.06
    Saved
    -0.06
    POSITIVE LOGITS
     mey
    0.07
    .dep
    0.07
     prostitution
    0.07
    桥
    0.06
     produce
    0.06
     acet
    0.06
     challenge
    0.06
     mission
    0.06
    Supplier
    0.06
    [],↵
    0.06
    Act Density 0.008%

    No Known Activations